© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 76003
    Prev
    Next
    INDEX
    Explanations

    amb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    使え
    -0.08
     предостав
    -0.07
    .AddTransient
    -0.07
    ady
    -0.07
    )index
    -0.07
    Bang
    -0.07
     program
    -0.07
    dig
    -0.06
    美誉
    -0.06
    中关村
    -0.06
    POSITIVE LOGITS
     ,,
    0.08
    先把
    0.08
    当作
    0.08
     לת
    0.07
    .model
    0.07
    				↵
    0.07
     الجمهور
    0.07
    بدء
    0.07
    一分
    0.07
     bottles
    0.07
    Activations Density 0.001%

    No Known Activations